ComfyUI
Open source · Image and video · Comfy-Org/ComfyUI
What it does
ComfyUI is an app for generating images, video and audio with open models, where you build the process as a graph of connected nodes. It runs locally and supports most popular open image and video models.
Good for: People who want full control over image or video generation on their own GPU.
ComfyUI on GitHub (opens in a new tab) Project homepage (opens in a new tab)
Visitor votes, one per browser. Your own vote is kept on this device only. How votes work.
The signals we checked
- Licence
- GPL-3.0 (OSI-approved open-source licence)
- Popularity
- Stars: 137,748 (checked 16 Oct 2026)
- Last commit
- 16 Oct 2026
- Open issues and PRs
- 5,205
- Status
- Active (not archived)
- Self-host
- ModerateDesktop installer or Python; a GPU is needed for usable speed.
- GitHub topics
- ai
- comfy
- comfyui
- python
- pytorch
- stable-diffusion
More in image and video
- Upscayl Upscaling product photos or old images without uploading them anywhere.
- Diffusers Developers adding image or video generation to their own Python code.
- InvokeAI Designers who want a friendlier local image tool with canvas editing.
- Wan 2.2 Experimenting with open text-to-video and image-to-video on serious hardware.
No affiliate links on this page, and we are not paid by this project. The summary is our own plain-English description; check the repo for current features before you rely on it.
Stars, licences and commit dates come from the GitHub API, checked 16 Oct 2026. "Last commit" is the last push to the repo. Star counts are a rough popularity signal, not a quality score. There are no affiliate links in this section: links go straight to each project.